deepseek-ocr
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
Görüntü
3b
⬇ 511.6K indirme · 3 varyant · 11.2025
Açık Kaynak AI Modelleri
Kendi bilgisayarınızda veya sunucunuzda ücretsiz çalıştırabileceğiniz modeller. Katalog ollama.com kütüphanesiyle canlı senkrondur · Son senkron: 13.08.2026 22:48.
233 model
cogito-2.1
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
671b
⬇ 220.2K indirme · 5 varyant · 11.2025
qwen3-vl
The most powerful vision-language model in the Qwen model family to date.
Görüntü
Araç Kullanımı
Akıl Yürütme
2b
4b
8b
30b
⬇ 5.2M indirme · 57 varyant · 10.2025
granite4
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
Araç Kullanımı
350m
1b
3b
⬇ 1.4M indirme · 17 varyant · 10.2025
gpt-oss-safeguard
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
Araç Kullanımı
Akıl Yürütme
20b
120b
⬇ 150.8K indirme · 3 varyant · 10.2025
qwen3
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
Araç Kullanımı
Akıl Yürütme
0.6b
1.7b
4b
8b
⬇ 34.1M indirme · 58 varyant · 10.2025
gpt-oss
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
Araç Kullanımı
Akıl Yürütme
20b
120b
⬇ 11.7M indirme · 5 varyant · 10.2025
deepseek-v3.1
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
Araç Kullanımı
Akıl Yürütme
671b
⬇ 720.5K indirme · 7 varyant · 09.2025
qwen3-embedding
Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
Embedding
0.6b
4b
8b
⬇ 3.6M indirme · 12 varyant · 09.2025
qwen3-coder
Alibaba's performant long context models for agentic and coding tasks.
Araç Kullanımı
30b
480b
⬇ 8.2M indirme · 9 varyant · 09.2025
embeddinggemma
EmbeddingGemma is a 300M parameter embedding model from Google.
Embedding
300m
⬇ 1.7M indirme · 5 varyant · 09.2025
gemma3
The current, most capable model that runs on a single GPU.
Görüntü
270m
1b
4b
12b
⬇ 39.5M indirme · 26 varyant · 08.2025
mistral-nemo
A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.
Araç Kullanımı
12b
⬇ 5.6M indirme · 17 varyant · 07.2025
mistral
The 7B model released by Mistral AI, updated to version 0.3.
Araç Kullanımı
7b
⬇ 31.9M indirme · 84 varyant · 07.2025
devstral
Devstral: the best open source model for coding agents
Araç Kullanımı
24b
⬇ 1M indirme · 5 varyant · 07.2025
deepseek-r1
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
Araç Kullanımı
Akıl Yürütme
1.5b
7b
8b
14b
⬇ 91.3M indirme · 35 varyant · 07.2025
gemma3n
Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.
e2b
e4b
⬇ 2M indirme · 9 varyant · 06.2025
mistral-small3.2
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
Görüntü
Araç Kullanımı
24b
⬇ 2.4M indirme · 5 varyant · 06.2025
magistral
Magistral is a small, efficient reasoning model with 24B parameters.
Araç Kullanımı
Akıl Yürütme
24b
⬇ 1.4M indirme · 5 varyant · 06.2025
llama4
Meta's latest collection of multimodal models.
Görüntü
Araç Kullanımı
16x17b
128x17b
⬇ 1.8M indirme · 11 varyant · 06.2025
qwen2.5-coder
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
Araç Kullanımı
0.5b
1.5b
3b
7b
⬇ 20.3M indirme · 199 varyant · 05.2025
qwen2.5vl
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
Görüntü
3b
7b
32b
72b
⬇ 4.1M indirme · 17 varyant · 05.2025
llama3.2-vision
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
Görüntü
11b
90b
⬇ 5M indirme · 9 varyant · 05.2025
phi4-reasoning
Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
14b
⬇ 1.7M indirme · 9 varyant · 05.2025
Açık kaynak model nasıl çalıştırılır?
Bu modeller Ollama ile tek komutla bilgisayarınızda çalışır (Windows, macOS, Linux). Verileriniz cihazınızdan çıkmaz — gizlilik gerektiren işler için idealdir.
- ollama.com/download adresinden Ollama'yı kurun
- Model sayfasındaki
ollama run …komutunu terminale yapıştırın - İlk indirme sonrası model tamamen çevrimdışı çalışır